A Comprehensive Review of Smart Agriculture Deep Neural Networks for Grapevine Earlier Disease Detection and Monitoring

Ashraf A. Mustafa; Araz Rajab Abrahim

doi:10.65542/djei.v2i2.34

Authors

Ashraf A. Mustafa Akre University for Applied Science, Technical College of Informatics, Akre, Department of Information Technology, Akre, Kurdistan Region, Iraq
Araz Rajab Abrahim Duhok Polytechnic University, Dean-Dohuk Technical Institute, Duhok, Kurdistan Region, Iraq, https://orcid.org/0009-0005-7671-0724

DOI:

https://doi.org/10.65542/djei.v2i2.34

Keywords:

CNN, Smart Agriculture, Disease Detection, Machine Learning, Deep Learning, Abstractive

Abstract

Deep learning is becoming increasingly important in many industries and has played a pivotal role in agriculture, particularly influencing viticulture. Convolutional neural networks (CNNs) have revolutionized disease detection and treatment in vineyards. Grapevines are vulnerable to various pathogens, including fungi, bacteria, and viruses, which cause heavy crop losses and pose economic risks to wine production. CNNs can detect diseases like powdery mildew and downy mildew several days earlier than symptoms appear, enabling timely treatment. Machine learning integrated into IoT-based environmental monitoring systems aids in building predictive algorithms that can forecast disease outbreaks based on weather records and history. Despite the potential for sustainability and higher profitability, challenges remain, such as data quality issues, insufficient model generalization across diverse environments, and high computational demands. To evaluate the current state of this technology, this study reviews over 30 peer-reviewed articles published between 2020 and 2024. The analysis reveals that while standard CNN models generally achieve accuracy levels above 90%, hybrid models combining CNNs with Long Short-Term Memory (LSTM) networks demonstrate superior performance, reaching accuracies of approximately 99%. Based on these findings, the review recommends that future research focus on validating models in real-world field conditions, enhancing generalizability across different geographical regions, and developing energy-efficient hardware for on-the-go disease detection. This review brings together findings of global research studies to provide an overall picture of deep learning's role in determining vineyard disease management's future.

References

Pinheiro, I.; Moreira, G.; Queirós da Silva, D.; Magalhães, S.; Valente, A.; Moura Oliveira, P.; Cunha, M.; Santos, F. Deep Learning YOLO-Based Solution for Grape Bunch Detection and Assessment of Biophysical Lesions. Agronomy, 13(4). 2023. doi: 10.3390/agronomy13041120

Messmer, N.; Bohnert, P.; Schumacher, S.; Fuchs, R. Studies on the occurrence of viruses in planting material of grapevines in southwestern Germany. Viruses, 13(2). 2021. doi: 10.3390/v13020248

Nuzzo, F.; Moine, A.; Nerva, L.; Pagliarani, C.; Perrone, I.; Boccacci, P.; Gribaudo, I.; Chitarra, W.; Gambino, G. Grapevine virome and production of healthy plants by somatic embryogenesis. Microbial Biotechnology, 15(5), 1357–1373. 2022. doi: 10.1111/1751-7915.14011

Porotikova, E.; Terehova, U.; Volodin, V.; Yurchenko, E.; Vinogradova, S. Distribution and genetic diversity of grapevine viruses in Russia. Plants, 10(6). 2021. doi: 10.3390/plants10061080

Dvorak, E.; Mazet, I.; Couture, C.; Foulongne-Oriol, M.; Delmotte, F. Crossing Plasmopara viticola strains in controlled conditions to uncover the genomic bases of downy mildew resistance breakdown in grapevine. BIO Web of Conferences, 50. 2022. doi: 10.1051/bioconf/20225002002

Pádua, L.; Adão, T.; Sousa, A.; Peres, E.; Sousa, J. J. Individual grapevine analysis in a multi-temporal context using UAV-based multi-sensor imagery. Remote Sensing, 12(1). 2020. doi: 10.3390/RS12010139

Palacios, F.; Diago, M. P.; Melo-Pinto, P.; Tardaguila, J. Early yield prediction in different grapevine varieties using computer vision and machine learning. Precision Agriculture, 24(2), 407–435. 2023. doi: 10.1007/s11119-022-09950-y

Elavarasan, D.; Durairaj Vincent, P. M. Crop Yield Prediction Using Deep Reinforcement Learning Model for Sustainable Agrarian Applications. IEEE Access, 8, 86886–86901. 2020. doi: 10.1109/ACCESS.2020.2992480

Hu, W. J.; Fan, J.; Du, Y. X.; Li, B. S.; Xiong, N.; Bekkering, E. MDFC-ResNet: An Agricultural IoT System to Accurately Recognize Crop Diseases. IEEE Access, 8, 115287–115298. 2020. doi: 10.1109/ACCESS.2020.3001237

Reis, S.; Fraga, H.; Carlos, C.; Silvestre, J.; Eiras-Dias, J.; Rodrigues, P.; Santos, J. A. Grapevine phenology in four portuguese wine regions: Modeling and predictions. Applied Sciences (Switzerland), 10(11). 2020. doi: 10.3390/app10113708

Andrew, J.; Eunice, J.; Popescu, D. E.; Chowdary, M. K.; Hemanth, J. Deep Learning-Based Leaf Disease Detection in Crops Using Images for Agricultural Applications. Agronomy, 12(10). 2022. doi: 10.3390/agronomy12102395

Cho, O. H. Machine Learning Algorithms for Early Detection of Legume Crop Disease. Legume Research, 47(3), 463–469. 2024. doi: 10.18805/LRF-788

Hernández, I.; Gutiérrez, S.; Tardaguila, J. Image analysis with deep learning for early detection of downy mildew in grapevine. Scientia Horticulturae, 331. 2024. doi: 10.1016/j.scienta.2024.113155

Li, R.; Liu, J.; Shi, B.; Zhao, H.; Li, Y.; Zheng, X.; Peng, C.; Lv, C. High-Performance Grape Disease Detection Method Using Multimodal Data and Parallel Activation Functions. Plants, 13(19). 2024. doi: 10.3390/plants13192720

Ukaegbu, U.; Tartibu, L.; Laseinde, T.; Okwu, M.; Olayode, I. A deep learning algorithm for detection of potassium deficiency in a red grapevine and spraying actuation using a raspberry pi3. In Proceedings of the 2020 International Conference on Communication and Signal Processing (ICCSP), Chennai, India. 2020. doi: 10.1109/ICCSP48568.2020.9183810

Prithiviraj, K.; Shakunthala, M.; Suneetha, C.; Lakshmi, T.; Venkatachalam, K.; Janardhan Saikumar, P. A Novel Approaches to Crop Variety Development for Sustainable Agriculture using Hybrid Machine Learning Model. Journal of Electrical Systems, 20(6s), 2811–2820. 2024. [DOI unavailable – please verify and add]

Ajmera, A.; Bhandari, M.; Jain, H. K.; Agarwal, S. Crop, Fertilizer, & Irrigation Recommendation using Machine Learning Techniques. International Journal for Research in Applied Science and Engineering Technology, 10(12), 29–35. 2022. doi: 10.22214/ijraset.2022.47793

Tang, J.; Yem, O.; Russell, F.; Stewart, C. A.; Lin, K.; Jayakody, H.; Ayres, M. R.; Sosnowski, M. R.; Whitty, M.; Petrie, P. R. Using a Camera System for the In-Situ Assessment of Cordon Dieback due to Grapevine Trunk Diseases. Australian Journal of Grape and Wine Research, 2023. 2023. doi: 10.1155/2023/8634742

Valori, R.; Costa, C.; Figorilli, S.; Ortenzi, L.; Manganiello, R.; Ciccoritti, R.; Cecchini, F.; Morassut, M.; Bevilacqua, N.; Colatosti, G.; Pica, G.; Cedroni, D.; Antonucci, F. Advanced Forecasting Modeling to Early Predict Powdery Mildew First Appearance in Different Vines Cultivars. Sustainability (Switzerland), 15(3). 2023. doi: 10.3390/su15032837

Ouhami, M.; Hafiane, A.; Es-Saady, Y.; El Hajji, M.; Canals, R. Computer vision, IoT and data fusion for crop disease detection using machine learning: A survey and ongoing research. In Remote Sensing (Vol. 13, Issue 13). MDPI AG. 2021. doi: 10.3390/rs13132486

Bendel, N.; Backhaus, A.; Kicherer, A.; Köckerling, J.; Maixner, M.; Jarausch, B.; Biancu, S.; Klück, H. C.; Seiffert, U.; Voegele, R. T.; Töpfer, R. Detection of two different grapevine yellows in Vitis vinifera using hyperspectral imaging. Remote Sensing, 12(24), 1–22. 2020. doi: 10.3390/rs12244151

Shahi, T. B.; Xu, C. Y.; Neupane, A.; Guo, W. Recent Advances in Crop Disease Detection Using UAV and Deep Learning Techniques. In Remote Sensing (Vol. 15, Issue 9). MDPI. 2023. doi: 10.3390/rs15092450

Hnatiuc, M.; Ghita, S.; Alpetri, D.; Ranca, A.; Artem, V.; Dina, I.; Cosma, M.; Abed Mohammed, M. Intelligent Grapevine Disease Detection Using IoT Sensor Network. Bioengineering, 10(9). 2023. doi: 10.3390/bioengineering10091021

Hernández, I.; Gutiérrez, S.; Barrio, I.; Íñiguez, R.; Tardaguila, J. In-field disease symptom detection and localisation using explainable deep learning: Use case for downy mildew in grapevine. Computers and Electronics in Agriculture, 226. 2024. doi: 10.1016/j.compag.2024.109478

Rodríguez-Díaz, F.; Chacón-Maldonado, A. M.; Troncoso-García, A. R.; Asencio-Cortés, G. Explainable olive grove and grapevine pest forecasting through machine learning-based classification and regression. Results in Engineering, 24. 2024. doi: 10.1016/j.rineng.2024.103058

Shokhrukh, T.; Sayyora, I.; Mohidil, A. Advanced detection and identification of grape pests and diseases using artificial intelligence. [URL INCORRECT: the listed URL (creativecommons.org/licenses/by-sa/4.0) is a Creative Commons license page, not the paper source. Please replace with the correct URL and publication year.]

Zhao, W.; Efremova, N. Grapevine Disease Prediction Using Climate Variables from Multi-Sensor Remote Sensing Imagery via a Transformer Model. Retrieved from http://arxiv.org/abs/2406.07094 2024.

Rudoy, D.; Olshevskaya, A.; Odabashyan, M.; Egyan, M.; Rybak, A.; Gapon, N.; Zhdanova, M.; Vershinina, A.; Marchenko, S. Analysis of grape (Vitis Vinifera) diseases using neural networks. BIO Web of Conferences, 113. 2024. doi: 10.1051/bioconf/202411301014

Khan, K. H.; Aljaedi, A.; Ishtiaq, M. S.; Imam, H.; Bassfar, Z.; Jamal, S. S. Disease Detection in Grape Cultivation Using Strategically Placed Cameras and Machine Learning Algorithms with a Focus on Powdery Mildew and Blotches. IEEE Access. 2024. doi: 10.1109/ACCESS.2024.3430190

Morellos, A.; Dolaptsis, K.; Tziotzios, G.; Pantazi, X. E.; Kateris, D.; Berruto, R.; Bochtis, D. An IoT Transfer Learning-Based Service for the Health Status Monitoring of Grapevines. Applied Sciences (Switzerland), 14(3). 2024. doi: 10.3390/app14031049

Kontogiannis, S.; Koundouras, S.; Pikridas, C. Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture. Computers, 13(3). 2024. doi: 10.3390/computers13030063

Karim, M. J.; Goni, M. O. F.; Nahiduzzaman, M.; Ahsan, M.; Haider, J.; Kowalski, M. Enhancing agriculture through real-time grape leaf disease classification via an edge device with a lightweight CNN architecture and Grad-CAM. Scientific Reports, 14(1). 2024. doi: 10.1038/s41598-024-66989-9

Elsherbiny, O.; Elaraby, A.; Alahmadi, M.; Hamdan, M.; Gao, J. Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning. Plants, 13(1). 2024. doi: 10.3390/plants13010135

Sharma, P.; Villegas-Diaz, R.; Fennell, A. Predicting Grapevine Physiological Parameters Using Hyperspectral Remote Sensing Integrated with Hybrid Convolutional Neural Network and Ensemble Stacked Regression. Remote Sensing, 16(14). 2024. doi: 10.3390/rs16142626

Özaltın, Ö.; Koyuncu, N. A Novel Feature Selection Approach-Based Sampling Theory on Grapevine Images Using Convolutional Neural Networks. Arabian Journal for Science and Engineering. 2024. doi: 10.1007/s13369-024-09192-2

Gentilhomme, T.; Villamizar, M.; Corre, J.; Odobez, J.-M. Towards smart pruning: ViNet, a deep-learning approach for grapevine structure estimation. Computers and Electronics in Agriculture, 207. 2023. doi: 10.1016/j.compag.2023.107736

Molnar, S.; Tamas, L. Segmentation Methods Evaluation on Grapevine Leaf Diseases. Proceedings of the 18th Conference on Computer Science and Intelligence Systems, FedCSIS 2023, 1081–1085. 2023. doi: 10.15439/2023F7053

Poblete-Echeverría, C.; Hernández, I.; Gutiérrez, S.; Iñiguez, R.; Barrio, I.; Tardaguila, J. Using artificial intelligence (AI) for grapevine disease detection based on images. BIO Web of Conferences, 68. 2023. doi: 10.1051/bioconf/20236801021

Zhang, Z.; Qiao, Y.; Guo, Y.; He, D. Deep Learning Based Automatic Grape Downy Mildew Detection. Frontiers in Plant Science, 13. 2022. doi: 10.3389/fpls.2022.872107

Sawyer, E.; Laroche-Pinel, E.; Flasco, M.; Cooper, M. L.; Corrales, B.; Fuchs, M.; Brillante, L. Phenotyping grapevine red blotch virus and grapevine leafroll-associated viruses before and after symptom expression through machine-learning analysis of hyperspectral images. Frontiers in Plant Science, 14. 2023. doi: 10.3389/fpls.2023.1117869

Pore, Y.; Arote, S.; Ayachit, S.; Bangar, N.; Ekhande, S. Grape Disease Detection Using Image Processing. International Journal of Scientific Research in Science and Technology, 11(5), 05–12. 2024. doi: 10.32628/IJSRST [incomplete – please verify the full DOI suffix and confirm volume/year]

Oprea, C. C.; Dragulinescu, A. M. C.; Marcu, I. M.; Pirnog, I. Evaluating Critical Disease Occurrence in Grapevine Leaves using CNN: Use-Case in Eastern Europe. 2023 17th International Conference on Engineering of Modern Electric Systems, EMES 2023. 2023. doi: 10.1109/EMES58375.2023.10171678

Kuznetsov, P. N.; Kotelnikov, D. Y.; Shchekin, V. Y.; Koltsov, A. D.; Kabankova, E. N. Intelligent complex of monitoring and diagnostics of grape plantations. IOP Conference Series: Earth and Environmental Science, 981(3). 2022. doi: 10.1088/1755-1315/981/3/032020

Liu, Y.; Su, J.; Zheng, Z.; Liu, D.; Song, Y.; Fang, Y.; Yang, P.; Su, B. GLDCNet: A novel convolutional neural network for grapevine leafroll disease recognition using UAV-based imagery. Computers and Electronics in Agriculture, 218. 2024. doi: 10.1016/j.compag.2024.108668